How to use hf-internal-testing/tiny-random-speech-encoder-decoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="hf-internal-testing/tiny-random-speech-encoder-decoder")
# Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-speech-encoder-decoder") model = AutoModelForSpeechSeq2Seq.from_pretrained("hf-internal-testing/tiny-random-speech-encoder-decoder")
What is a pickle import?
